解决Tika Server上下文路径问题：基于Spring Boot的替代方案

<!-- pom.xml -->
<dependencies>
    <!-- Spring Boot Web Starter -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>

    <!-- Apache Tika Parsers -->
    <dependency>
        <groupId>org.apache.tika</groupId>
        <artifactId>tika-parsers</artifactId>
        <version>2.9.0</version> <!-- 请替换为当前最新稳定版本 -->
    </dependency>

    <!-- 其他依赖，如Spring Boot DevTools等 -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-test</artifactId>
        <scope>test</scope>
    </dependency>
</dependencies>

# application.properties
server.port=8080
server.servlet.context-path=/tika-proxy

// src/main/java/com/example/tika/TikaServiceController.java
package com.example.tika;

import org.apache.tika.Tika;
import org.apache.tika.exception.TikaException;
import org.apache.tika.io.TikaInputStream;
import org.springframework.http.HttpStatus;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;

import java.io.IOException;
import java.io.InputStream;

@RestController
@RequestMapping("/api/tika") // 可选：在上下文路径之后再添加一层API路径
public class TikaServiceController {

    private final Tika tika = new Tika();

    /**
     * 检测上传文件的内容类型。
     * @param file 上传的文件
     * @return 文件的内容类型
     */
    @PostMapping(value = "/detect-type", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public ResponseEntity<String> detectContentType(@RequestParam("file") MultipartFile file) {
        if (file.isEmpty()) {
            return new ResponseEntity<>("Please select a file to upload.", HttpStatus.BAD_REQUEST);
        }
        try (InputStream stream = file.getInputStream()) {
            String contentType = tika.detect(stream, file.getOriginalFilename());
            return new ResponseEntity<>(contentType, HttpStatus.OK);
        } catch (IOException e) {
            return new ResponseEntity<>("Error detecting content type: " + e.getMessage(), HttpStatus.INTERNAL_SERVER_ERROR);
        }
    }

    /**
     * 提取上传文件的文本内容。
     * @param file 上传的文件
     * @return 提取到的文本内容
     */
    @PostMapping(value = "/extract-text", consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
    public ResponseEntity<String> extractText(@RequestParam("file") MultipartFile file) {
        if (file.isEmpty()) {
            return new ResponseEntity<>("Please select a file to upload.", HttpStatus.BAD_REQUEST);
        }
        try (InputStream stream = file.getInputStream();
             TikaInputStream tikaStream = TikaInputStream.get(stream)) {
            String extractedText = tika.parseToString(tikaStream);
            return new ResponseEntity<>(extractedText, HttpStatus.OK);
        } catch (IOException | TikaException e) {
            return new ResponseEntity<>("Error extracting text: " + e.getMessage(), HttpStatus.INTERNAL_SERVER_ERROR);
        }
    }

    // 可以根据需要添加更多Tika功能，例如元数据提取等
}